In this project I have tried to use actor-critic Reinforcement learning strategy to attempt to optimize returns over a run of two correlated stocks(AAPL & MSFT).
-
The concept of Actor Critic Reinforcement Learning is quite popular and seems to work well when we have both an infinite input space and an infinite output space, which is the case for stock market.
-
The actor takes in the current environment state and determines the best action to take, the critic plays the evaluation role by taking in the environment state and action, returning an action score.
-
Actor-Critic methods need less training time than policy gradient methods.